Sep 2024 - First Principles

  • Host: Christian Keil
  • Links: X
  • Summary: A sit-down interview with Christian Keil where I explain robot actuator safety from first principles and how 1X thinks about vertically integrated hardware and software.

Mar 2024 - Data Engines for Humanoid Robots

  • Host: GRASP Lab Seminar Series
  • Links: Youtube
  • Summary: An invited talk I gave at UPenn’s GRASP Lab on 1X’s AI progress. We have scaled up the number of tasks our androids can do by combining an end-to-end learning strategy with a no-code system to add new robotic capabilities. Our Android Operations team trains their own models on the data they gather themselves, producing an extremely high-quality “farm-to-table” dataset that can be used to learn extremely capable behaviors.

Jan 2024 - The Gradient Podcast

  • Host: Daniel Bashir
  • Links: Youtube Substack Spotify
  • Summary: A guest podcast interview on The Gradient where Daniel and I chat about technical challenges in implementing humanoid robots and artificial life.

Dec 2023 - Tomorrow Talk

  • Host: Sabrina Halper
  • Links: Youtube Spotify
  • Summary: A guest podcast interview on the Tomorrow Talk podcast where Sabrina and I chat about artificial general intelligence, robots, and the future of AI as covered in my book.

Jun 2022 - RSS Workshop on Learning from Diverse Offline Datasets

Jun 2022 - Fireside Chat for RSS

  • Host: Peter Fagan
  • Links: Video
  • Summary: We discuss big-picture aspects of robotic deep learning, such as why robotic imitation learning makes sense from a product standpoint.

Jan 2022 - Casual Robotics

  • Host: Kevin Zakka
  • Guests: Pete Florence and myself
  • Summary: We discuss progress in robotics in the last 50 years, and the roles software and hardware have played in this development. On the algorithmic side, we discuss how much of imitation learning and reinforcement learning is needed to obtain general purpose robots and why policy evaluation is hard in the real-world.
  • Links: Spotify

Jan 2022 - The Gradient Podcast

  • Host: Andrey Kurenkov
  • Summary: We cover how I got into AI research (starting from neuroscience!) and the hard-won lessons I learned from my first few projects at Google. This is a summary of what I have learned about robotic deep learning in the last 5-6 years. Hopefully folks who are curious about what a “5-year growth trajectory, starting from 0 experience” find this useful.
  • Links: Substack, Apple Podcasts, Spotify

Dec 2021 - Bits of Deep Learning Podcast

  • Host: Andrea Lonza
  • Summary: I discuss my opinions on “the most important problem in robotics”, Reinforcement Learning vs. Imitation Learning vs. Self-Supervised Learning”, & “Just ask for Generalization”.
  • Links: YouTube

Dec 2021 - Stitch Fix Algo Hour

  • Host: Stitch Fix
  • Summary: I give a talk version of the ideas behind my blog posts “Just ask for Generalization” and “To Understand Language is to Understand Generalization”.
  • Links: YouTube

Jun 2019 - Tutorial on Normalizing Flows

  • Host: ICML 2019 Workshop on Invertible Generative Models
  • Links: slideslive.com

Jan 2019 - Deep Learning for Robotics and Robotics for Deep Learning